© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141602
    Prev
    Next
    INDEX
    Explanations

    Thank you for questions

    np_acts-logits-general · gemini-2.5-flash-lite

    Function, Chorus, leaves, vapor, transcribe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     遊ん
    0.52
    гает
    0.48
     tarixi
    0.47
    ܂
    0.47
    gah
    0.47
    usammen
    0.46
    halle
    0.46
     mengadakan
    0.45
    ACING
    0.45
    ᱾
    0.45
    POSITIVE LOGITS
     Prince
    0.52
     Friday
    0.49
     Cairo
    0.48
     Plumbing
    0.48
     Thurs
    0.46
     Eng
    0.46
     Thursday
    0.46
     Uranus
    0.46
     Pretoria
    0.46
     Magnus
    0.45
    Activations Density 0.001%

    No Known Activations